AI agents use add_relationship_to_role to create or update resources in Smokeball — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Smokeball environment.
Adding a contact relationship is a reversible data modification operation — relationships can be removed or changed. It does not delete data (Destructive), does not execute arbitrary code (Execute), does not move money (Financial), and does not merely retrieve information (Read).
From the tool's definition Tool description states 'Add a contact relationship to a role on a matter' — this is a create/add operation that modifies data (establishes relationships between contacts and roles).
Attacks that exploit this kind of access
Add a contact relationship to a role on a matter. It is categorised as a Write tool in the Smokeball MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Smokeball MCP server in PolicyLayer and add a rule for add_relationship_to_role: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Smokeball. Nothing to install.
add_relationship_to_role is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_relationship_to_role rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for add_relationship_to_role. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
add_relationship_to_role is provided by the Smokeball MCP server (rosenadvertising/smokeball-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →